atom-agent 1.0.0 → 1.2.0

package/CHANGELOG.md

@@ -1,8 +1,68 @@
 # Changelog
 
-## Unreleased
+## 1.2.0 — 2026-09-10
 
-(nothing yet)
+- Durable multi-session store (`src/sessions.ts`): one JSON record per
+  session under `~/.atom/sessions/<id>.json` plus a plaintext `active`
+  pointer. Records carry stable `ses_` ids (never derived from the display
+  name), mutable titles defaulting to the exact local creation date and
+  time, separate machine-readable `createdAt`, `updatedAt` on every
+  meaningful mutation, `cwd`, provider/model/effort/mode, usage, full
+  history/turns, and metadata. Atomic temp-plus-rename writes (`0600`
+  POSIX), loads that never throw, most-recent-first listings, no transient
+  UI state, no LLM provider coupling
+- `/rename <name>` (current session only; quotes optional; bare prints
+  usage): id, `createdAt`, and history untouched, persisted immediately,
+  failures keep the previous name
+- `/session [filter]` interactive switcher: most-recent-first picker with
+  in-memory fuzzy filter (title first, id fallback), turn counts, relative
+  ages, `(current)` marker, windowing for large lists. Selecting replaces
+  the live conversation wholesale (no merge, no duplication) with
+  provider/model/settings restored; the outgoing turns snapshot first,
+  checkpoints and the TODO checklist reset like `/new`, and a missing
+  target errors without touching the live session. `Esc` cancels cleanly
+- Runtime integration (`src/App.tsx`): every conversation auto-belongs to
+  the active session; completed turns, exits, and compactions mirror into
+  the record; `/new` snapshots then swaps records; the legacy
+  `session.json` save follows switches so `/resume` stays coherent.
+  Session identity surfaces in the picker, confirmations, and the
+  empty-state line (the status bar keeps its fixed width budget)
+- Suite: `session-store` (26), `sessions-runtime` (5), `rename` (8),
+  `session-picker` (11), `session-lifecycle` (4) — see
+  `documentation/sessions.md`
+
+## 1.1.0 — 2026-09-10
+
+- Agentic loop hardening (`src/agent/loop.ts`, `types.ts`, `loop-guard.ts`,
+  `normalize.ts`; `src/zen.ts`, `adapters.ts`): tool-result and
+  model-response normalization, per-tool execution timeouts, total tool-call
+  budget per turn, error-streak recovery (holds final text for a fix-forward
+  attempt instead of ending on unaddressed failures), opt-in repetition guard
+  with background-poll exclusions, and a per-turn `LoopStats` rollup
+  (iterations, calls, failures, cache hits, guard hits, bottleneck, context
+  growth) reported via `AgenticOpts.onLoopStats`, even on failed turns.
+  SSE stall guard (`ATOM_STALL_TIMEOUT_MS`, default 60s) in every streaming
+  reader: a silent 200-OK stream fails fast on the permanent Truncated
+  contract instead of hanging the turn
+- LoopStats into observability (`src/telemetry.ts`,
+  `telemetry-dashboard.ts`, `src/App.tsx`): `recordLoopStats` attaches the
+  harness rollup to the open turn trace, aggregates total cache/guard hits,
+  dashboard renders per-turn loop fragments plus overview cards
+- Search speed (`src/tools/search.ts`, `dir-cache.ts`, `read-cache.ts`,
+  `filesystem.ts`, `shell.ts`): `git ls-files` enumeration (tracked plus
+  untracked-non-ignored, `node_modules`/`.git` still excluded), single-pass
+  grep (half the file reads), 32-wide bounded-parallel scan with identical
+  output order, mtime-checked listing cache with exact invalidation on
+  write/edit/bash (`ATOM_FAST_LIST=0` forces the legacy walker), and a
+  stat-validated read cache. Measured 3–7x on content search; batching nudge
+  added to the system prompt
+- TUI flow (`src/App.tsx`, `ui/transcript.tsx`, `live-tail.tsx`,
+  `status-bar.tsx`, `todo-panel.tsx`, `modals.tsx`, `palette.tsx`):
+  `/autoscroll on|off` (freezes a following view mid-turn instead of yanking
+  it), `/thinking` toggle with per-round model reasoning persisted to the
+  transcript (rendering-only; never model history), memoized status bar,
+  todo panel, approval/question modals, and palette plus memoized
+  palette/checkpoint derivations (timer-tick and picker-nav flicker fix)
 
 ## 1.0.0 — 2026-09-09
 

package/README.md

@@ -26,10 +26,10 @@ Full docs live in [`documentation/`](documentation/index.md), same layout as ope
 - [Getting Started](documentation/getting-started.md) — install, key setup, first run
 - [CLI and TUI](documentation/cli.md) — slash commands, keyboard, status line
 - [Tools](documentation/tools.md) — the 13 local executors, caps, background tasks
-- [Providers and Models](documentation/providers.md) — 8 providers, endpoints, key resolution (Kilo default, key-optional)
-- [Permissions and Modes](documentation/permissions.md) — normal/yolo, trust, allow/deny rules
+- [Providers and Models](documentation/providers.md) — 8 remote providers + 3 local runtimes, endpoints, key resolution (Kilo default, key-optional)
+- [Permissions and Modes](documentation/permissions.md) — normal/yolo/plan, trust, allow/deny rules
 - [Skills](documentation/skills.md) — discovery, frontmatter contract, auto-invoke
-- [Sessions](documentation/sessions.md) — persistence, resume, clear, rewind
+- [Sessions](documentation/sessions.md) — durable multi-session store, rename, switcher, resume, clear, rewind
 - [Observability](documentation/observability.md) — local telemetry, `/telemetry`, dashboard drill-down
 - [Compaction and Token Display](documentation/compaction.md) — auto-compact, manual compact, footer format
 - [Configuration](documentation/configuration.md) — env vars, auth file, AGENTS.md layering
@@ -89,7 +89,7 @@ in `package.json`, add a `CHANGELOG.md` entry, commit, tag `vX.Y.Z`, push —
 ## What Atom can do
 
 - 🤖 **Agentic loop** — tool calls execute locally and results feed back in,
-  up to 30 steps per turn (`ATOM_MAX_TOOL_STEPS`, clamped 5–100), with retries on transient failures
+  with no step cap by default (optional cap via `ATOM_MAX_TOOL_STEPS`, clamped 5–100), with retries on transient failures
 - ⚡ **Streaming** — tokens, tool activity, and phase status render live;
   reasoning streams in its own dim block above the answer draft
   (transient); `Esc` stops a running response (footer shows `esc stops`
@@ -98,23 +98,23 @@ in `package.json`, add a `CHANGELOG.md` entry, commit, tag `vX.Y.Z`, push —
   `bash_output`, `websearch`, `webfetch`, `ask_question` (asks *you* things
   interactively), `todowrite` / `todo_get` / `todo_update` (session task
   checklist with a live TUI panel)
-- 🛡️ **Normal / YOLO modes** — `Tab` toggles. Normal auto-runs reads but
+- 🛡️ **Normal / YOLO modes** — `Tab` cycles normal → yolo → plan → normal. Normal auto-runs reads but
   asks before writes/shell (`y` once · `a` always · `t` trust all · `n` deny);
   `/trust` toggles a session trust tier (one approval covers the whole task,
   status shows `+trust`, never saved). YOLO never asks
-- 🗺️ **Plan mode** — `/plan` enters a read-only mode for risky work:
+- 🗺️ **Plan mode** — `Tab` from yolo enters a read-only mode for risky work:
   exploration (`read`/`grep`/`glob`/web/todos/`ask_question`) runs free while
   `write`/`edit`/`bash` are blocked pre-execution with a replan note (never a
-  prompt). `Tab` never enters/exits plan, `/yolo`·`/trust` can't punch through
-  it, `/deny` still wins. Exiting `/plan` approves the recorded todo checklist
+  prompt). `/yolo`·`/trust` can't punch through
+  it, `/deny` still wins. `Tab` out of plan approves the recorded todo checklist
   into implementation (lands in normal, never yolo)
 - ⌨️ **Slash commands** — `/model` (unified picker across keyed providers,
   type to filter), `/provider` (provider + key picker, keys in
   `~/.atom/auth.json`), `/effort` (reasoning-effort picker), `/tools`,
   `/skills`, `/skill:name` (invoke a skill; skills complete in `/`), `/context`
   (context usage by source), `/queue` + `/steer <text>` (follow-ups while
-  busy: queue until the turn ends, or inject into the running turn), `/help`, `/mode`, `/yolo`, `/trust`, `/plan`,
-  `/clear`, `/exit` — plus `/`-autocomplete as you type
+  busy: queue until the turn ends, or inject into the running turn), `/help`, `/mode`, `/trust`,
+  `/clear`, `/exit` — plus `/`-autocomplete as you type (`/yolo` and `/plan` are retired as typed commands — `Tab` switches modes)
 - 📊 **Status line** — provider · model · session token usage (`token:
   (P%) NK`: NK is the cumulative spend in K, P% is the current context load
   over the model's verified window — last `prompt_tokens`, else the
@@ -174,7 +174,7 @@ auto-approved call).
 
 Full reference: [Providers and Models](documentation/providers.md) plus [Configuration](documentation/configuration.md).
 
-Atom talks to 8 providers behind one UI (opencode `/connect` mirror,
+Atom talks to 8 remote providers plus 3 local runtimes (Ollama, LM Studio, llama.cpp) behind one UI (opencode `/connect` mirror,
 manual-key only — no OAuth). Kilo Gateway is the default: its free models
 (`:free` ids, incl. the `kilo-auto/free` routing model) chat with no key;
 paste a key once with `/provider` (validated, stored in
@@ -227,7 +227,7 @@ npm run build    # emit dist/ (the `atom` binary entry is dist/cli.js)
 
 Env knobs: `KILO_API_KEY` (optional; or stored Kilo key via `/provider`), `OPENCODE_ZEN_API_KEY` (or stored zen key via `/provider`), `OPENCODE_ZEN_MODEL`,
 `OPENCODE_ZEN_ENDPOINT`, `OPENCODE_AGENTS_PATH`, `ATOM_COMPACT_PCT` (auto-compact percent, 50–95),
-`ATOM_MAX_TOOL_STEPS` (tool rounds per turn, default 30, clamped 5–100),
+`ATOM_MAX_TOOL_STEPS` (optional cap on tool rounds per turn, clamped 5–100),
 plus per-provider key env vars above.
 `~/.atom/auth.json` holds pasted keys (`{version:1, providers:{"<id>":{apiKey, baseURL?}}}`, `0600` POSIX).
 
@@ -235,21 +235,22 @@ plus per-provider key env vars above.
 .
 ├── src/
 │   ├── cli.tsx    # entry: --help/--dashboard/--serve, always starts TUI (missing key guides to /provider)
-│   ├── App.tsx    # Ink TUI: transcript, pickers, modes (/plan /trust), approvals, status line
+│   ├── App.tsx    # Ink TUI: transcript, pickers, Tab modes, /trust, approvals, status line
 │   ├── telemetry.ts # local observability recorder + store (never throws, off via ATOM_TELEMETRY=0)
 │   ├── telemetry-dashboard.ts # self-contained local dashboard page (session → turn → iteration → call)
-│   ├── zen.ts     # agentic loop (budgets, todo/verification guards) + provider dispatch + SSE
+│   ├── zen.ts     # provider dispatch + agentic-loop wrappers (shared core in src/agent/loop.ts) + SSE
 │   ├── tools.ts   # 13 local tool executors + function schemas (read/write/edit/grep/glob/bash/…)
 │   ├── permissions.ts # allow/deny rule matcher backing /allow /deny /rules
 │   ├── snapshots.ts   # pre-mutation file snapshots backing /rewind
 │   ├── skills.ts  # skill discovery backing /skills
 │   ├── env-block.ts   # per-turn cwd/git/node environment block
-│   ├── providers.ts # 8-provider registry (kind/endpoint/env/default + fallback models; Kilo default)
+│   ├── providers.ts # 8 remote providers + 3 local runtimes (kind/endpoint/env/default + fallback models; Kilo default)
 │   ├── kilo.ts      # Kilo Gateway: catalog parsing, free detection, TTL cache, error normalization
 │   ├── auth.ts    # ~/.atom/auth.json store (env wins, 0600 POSIX)
 │   ├── adapters.ts # anthropic/gemini translation + SSE + models-list parsing + key validation
 │   ├── compact.ts # context compaction: load/trigger math, split, summary POST (tools off)
-│   ├── session.ts # session save/resume
+  │   ├── session.ts # legacy single-file save/resume (session.json)
+  │   ├── sessions.ts # durable multi-session store (sessions/, /rename, /session picker)
 │   ├── context-windows.ts # curated per-model context windows + `token: (P%) NK` format
 │   └── system.ts  # base system prompt (long-horizon operating contract)
 ├── dist/          # `npm run build` output (`atom` runs dist/cli.js; gitignored, shipped in the tarball)